Skip to main content
Glama

Server Details

LinkedIn outreach from Claude: invites under safe caps, follow-ups, replies and inbox triage.

Ownership verified

The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Uptime
0.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP
URL
ChatGPT
–
Claude
–

TDQS

A4.1/5.0

Scored across 104 tools

Disambiguation4/5

Given ~100 tools in one domain, the boundaries are unusually explicit: descriptions name their neighbours and say when NOT to use a tool (li_cancel_steps vs li_mark_stopped, li_conversation_history vs li_read_conversation, li_send_reply vs li_send_message vs li_send_bulk_messages, li_check_targets vs the built-in collision report). Overlap remains in the read surfaces — list_conversations / read_conversation / read_conversations_bulk / conversation_history / replies_to_answer all expose threads — and several near-synonym pairs (li_pending_invites vs li_connections, li_connections vs li_new_connections) require careful reading rather than being self-evident from the name.

Naming Consistency4/5

Almost everything follows li_<verb>_<noun> snake_case (li_create_campaign, li_mark_outcome, li_cancel_steps), with the li_ prefix applied uniformly across all 104 tools. Deviations are few but real: a handful are bare nouns or noun phrases (li_connections, li_bookings, li_proxies, li_replies_to_answer, li_account_activity, li_outcome_summary, li_selector_canary), so the verb is not always predictive of read-vs-write.

Tool Count1/5

At 104 tools this is far past any practical ceiling for reliable agent selection, and the surface spans at least four unrelated domains in one server: outreach operations, enrichment/research, triage, and operator-only billing/proxy/infrastructure admin. Whole clusters could be collapsed (e.g. one conversation-read tool with a scope flag, one bulk-vs-single send, one campaign-create/ingest) rather than each variant being its own tool.

Completeness5/5

Every lifecycle has full coverage including the awkward parts: create/edit/cancel/launch/pause/resume campaigns, hold steps, reset contacts, undo mistaken marks, per-person and campaign-wide copy edits, dry-run previews, pagination with explicit truncation flags, and job-based recovery for timed-out async work. Operator surfaces (billing, proxies, invites breaker, health) and safety surfaces (do-not-contact, install-wide holds, send confirmations) are all present rather than left as gaps.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      AI agent for LinkedIn outreach: finds the right people, writes in your voice, follows up, replies. Six campaign goals: sell a product or service, find a job, hire people, find partners or investors, find a vendor, research interviews. Campaigns stay drafts until you launch them.
      22
      4,076 PyPI
      13
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables automated LinkedIn growth by posting, commenting, and managing connections through Claude Code, with daily scheduled tasks for inbox replies and connection requests.
      17
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      LinkedIn prospect intelligence inside Claude. It automates the research behind outreach, not the sending: scrapes posts, profiles and comment threads into a local SQLite database, classifies what a person or company actually posts about, mines comment threads for people already describing your problem, and surfaces uncommon commonalities worth opening with.
      18
      34
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources